CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

create-cli

CLI UX/spec: args, flags, help, output, errors, config, dry-run.

61

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/create-cli/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an exemplary lean, directive skill: concrete conventions, explicit defaults, and a copy-paste spec template with a clear read-then-clarify-then-produce workflow. Its main gaps are the absence of a worked example invocation, no validation step for the produced spec, and a reference path that does not match the bundle's actual layout.

Suggestions

Fix the reference path to be bundle-relative: 'Read `references/cli-guidelines.md`...' so it resolves from the skill's own directory instead of the non-existent `agent-scripts/skills/create-cli/` prefix.

Add one worked mini-example (a filled-in fragment of the spec skeleton or 2-3 sample invocations) so the '5-10 example invocations' deliverable is demonstrated, not just mandated.

Add a final validation step, e.g. 'Before delivering, check the spec against the guidelines reference (help/exit codes/stdout-vs-stderr/dry-run) and fix any violations', closing the workflow's feedback loop.

DimensionReasoningScore

Conciseness

The body is lean and directive throughout — terse bullets like '- Primary data to stdout; diagnostics/errors to stderr' and '- Respect `NO_COLOR`, `TERM=dumb`; provide `--no-color`' with zero padding and no explanation of concepts Claude already knows, matching the anchor for every token earning its place.

5 / 5

Actionability

Guidance is highly concrete and executable — specific flags (`--no-input`, `--json`, `--plain`, `--force`), concrete exit codes (0/1/2), an explicit precedence order ('flags > env > project config > user config > system'), and a copy-paste spec skeleton — but no example invocations are shown inline (the skill mandates '5-10 example invocations' without demonstrating one), which leaves it just short of the 'specific examples cover the common cases' anchor 5.

4 / 5

Workflow Clarity

The sequence is clear and well-ordered (Do This First → Clarify with best-guess defaults → Deliverables → Default Conventions → Template → Notes), and the 'Ask, then proceed with best-guess defaults if user is unsure' fallback acts as a decision checkpoint; however there is no explicit validation step reviewing the produced spec against the guidelines, fitting anchor 4 (clear sequence, minor validation gaps) rather than 5.

4 / 5

Progressive Disclosure

The single reference is clearly signaled ('Read `agent-scripts/skills/create-cli/references/cli-guidelines.md` and apply it as the default rubric') and is one level deep, but the path given does not resolve to the actual bundle location (`references/cli-guidelines.md`), a navigational gap that keeps it at anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Description

61%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is a terse, keyword-dense tagline that clearly identifies the CLI-design niche and includes natural trigger terms, but it omits any explicit 'when to use' guidance and contains no action verbs, limiting both completeness and specificity. It reads more like a compressed index than a full capability statement.

Suggestions

Add an explicit trigger clause, e.g. 'Use when designing or reviewing a command-line tool's interface — arguments, flags, help text, output format, errors, exit codes, config, or dry-run behavior.'

Convert the noun list into action verbs to raise specificity, e.g. 'Designs CLI syntax and behavior: defines args/flags, help output, stdout/stderr contracts, error and exit-code maps, config precedence, and dry-run/confirmation safety.'

Include common synonyms such as 'command line interface', 'subcommands', and 'exit codes' so natural phrasings users actually say also match the trigger terms.

DimensionReasoningScore

Specificity

The description names the domain ('CLI UX/spec') and lists concrete facets ('args, flags, help, output, errors, config, dry-run'), but presents them as noun keywords with no action verbs at all — it falls between anchor 3 (domain + minimal actions) and anchor 4 (several specific actions), and the absence of any verb phrasing keeps it at 3 rather than 4.

3 / 5

Completeness

The 'what' is present and reasonably clear (CLI UX/spec covering args, flags, help, output, errors, config, dry-run), but there is no 'Use when...' clause or any equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines; it is not 4 because 'when' is entirely absent rather than merely under-specified.

3 / 5

Trigger Term Quality

Terms like 'args', 'flags', 'help', 'output', 'errors', 'config', and 'dry-run' are exactly what users say when designing a command-line tool, giving good keyword coverage; a few natural variants are missing ('command line', 'subcommands', 'exit codes', 'design a CLI'), which fits anchor 4 rather than the comprehensive synonym coverage of 5.

4 / 5

Distinctiveness Conflict Risk

'CLI', 'args', 'flags', and 'dry-run' carve out a clear niche with minimal conflict risk, but 'output', 'errors', and 'config' are generic terms that overlap with many other skills, matching anchor 4 (mostly distinct, minor overlap risk) rather than 5.

4 / 5

Total

14

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

steipete/agent-scripts

Path

skills/create-cli/SKILL.md

Revision

d602e8a

Reviewed

Table of Contents

DiscoveryImplementationValidation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.

Claim skill